Models for multiparty engagement in open-world dialog

Bohus, Dan; Horvitz, Eric

doi:10.3115/1708376.1708409

Cited by 98 publications

(105 citation statements)

References 6 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…More sophisticated strategies for addressing a system in a multi-party dialogue context have been 135 studied [28,29], but they are beyond the scope of this paper, which is concerned with processing the query itself. Once the results are generated by the system, they are displayed on each user's device (typically the laptop they use during the meeting) or on a shared projection screen.…”

Section: Content-based Query Refinementmentioning

confidence: 99%

Question answering in conversations: Query refinement using contextual and semantic information

Habibi

Mahdabi

Popescu-Belis

2016

Data & Knowledge Engineering

View full text Add to dashboard Cite

This paper introduces a query refinement method applied to questions asked by users to a system during a meeting or a conversation that they have with other users. To answer the questions, the proposed method leverages the local context of the conversation along with semantic resources, either WordNet or word embeddings from word2vec. The method first represents the local context by extracting keywords from the transcript of the conversation, which is obtained from a real-time Automatic Speech Recognition (ASR) system and may contain noise. It then expands the queries with keywords that best represent the topic of the query, i.e. expansion keywords accompanied by weights indicating their topical similarity to the query. Finally, semantically related terms are added, using two options: either synonymous terms drawn from WordNet or similar words based on distributed representations in a low-dimensional word embedding space learned using word2vec. To evaluate the system, we introduce a dataset (named AREX for AMI Requests for Explanations) and an evaluation metric based on relevance judgments collected by crowdsourcing. We compare our query expansion approach with other methods, over queries from the AREX dataset, showing the superiority of our method when either manual or automatic transcripts of the AMI Meeting Corpus are used.

show abstract

Section: Content-based Query Refinementmentioning

confidence: 99%

Question answering in conversations: Query refinement using contextual and semantic information

Habibi

Mahdabi

Popescu-Belis

2016

Data & Knowledge Engineering

View full text Add to dashboard Cite

show abstract

“…The users can simply address the system by using a pre-defined unambiguous name, which is robustly recognized by a real-time ASR component [14]. More sophisticated strategies for addressing a system in a multi-party dialogue context have been studied [6,28], but they are beyond the scope of this paper, which is concerned with the processing of the query itself by the system. Once the results are generated by the system, they are displayed on a shared projection screen or on each user's device.…”

Section: Content-based Query Refinementmentioning

confidence: 99%

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Habibi

Popescu-Belis

2015

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

Abstract. This paper introduces a query refinement method applied to queries asked by users during a meeting or a conversation. Current approaches suffer from poor quality to achieve this goal, but we argue that their performance could be improved by focusing on the local context of the conversation. The proposed technique first represents the local context by extracting keywords from the transcript of the conversation. It then expands the queries with keywords that best represent the topic of the query (e.g. pairs of expansion keywords together with a weight indicating their topical similarity to the query). Moreover, we present a dataset called AREX and an evaluation metric. We compared our query expansion approach with other methods, on topics extracted from the AREX dataset and based on relevance judgments collected in a crowdsourcing experiment. The comparisons indicate the superiority of our method on both manual and ASR transcripts of the AMI Meeting Corpus.

show abstract

“…The remaining works mostly take a very simplified version of the problem or do not explicitly mention VFOA recognition at all. For instance, in [7], [6] it is not mentioned how the VFOA is extracted and it is only used by the other modules. In [6] the problem is relaxed by only inquiring if the person is looking at the system or not.…”

Section: Related Workmentioning

confidence: 99%

“…For instance, in [7], [6] it is not mentioned how the VFOA is extracted and it is only used by the other modules. In [6] the problem is relaxed by only inquiring if the person is looking at the system or not. In [13] detecting a frontal face at a suitable spatial location is enough to adjust the classification to a higher level of engagement.…”

Section: Related Workmentioning

confidence: 99%

Recognizing the Visual Focus of Attention for Human Robot Interaction

Sheikhi

Odobez

2012

Human Behavior Understanding

View full text Add to dashboard Cite

Abstract. We address the recognition of people's visual focus of attention (VFOA), the discrete version of gaze that indicates who is looking at whom or what. As a good indicator of addressee-hood (who speaks to whom, and in particular is a person speaking to the robot) and of people's interest, VFOA is an important cue for supporting dialog modelling in Human-Robot interactions involving multiple persons. In absence of high definition images, we rely on people's head pose to recognize the VFOA. Rather than assuming a fixed mapping between head pose directions and gaze target directions, we investigate models that perform a dynamic (temporal) mapping implicitly accounting for varying body/shoulder orientations of a person over time, as well as unsupervised adaptation. Evaluated on a public dataset and on data recorded with the humanoid robot Nao, the method exhibit better adaptivity and versatility producing equal or better performance than a state-of-the-art approach, while the proposed unsupervised adaptation does not improve results.

show abstract

Models for multiparty engagement in open-world dialog

Cited by 98 publications

References 6 publications

Question answering in conversations: Query refinement using contextual and semantic information

Question answering in conversations: Query refinement using contextual and semantic information

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Recognizing the Visual Focus of Attention for Human Robot Interaction

Contact Info

Product

Resources

About